mlsanityData to 7 Oct 2026

Agentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems

arXiv 2606.24416 ↗First posted 23 Jun 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agentic AI for wireless networks

Abstract (arXiv)

Network operators' changing policies, service requirements, and stringent real-time constraints render existing methods designed with fixed objectives and constraints ineffective. This paper presents Agentic long-term performance optimization (Agentic-LTPO), a nested bilevel optimization framework that can be applied to adaptive physical layer problem configuration. The key idea is to employ agentic AI to generate upper-level configurations in a bilevel optimization structure, where evolving operator policies, environment summaries, and historical experiences are translated into structured lower-level optimization problem configurations. The lower level solves the problems with updated configurations for real-time physical-layer decisions. Considering cell-free MIMO beamforming as a use case, we embody Agentic-LTPO by designing a new multi-agent decision process with retrieval-augmented experience-based verification in the upper level, together with a closed-form beamformer in the lower level. Experiments demonstrate that Agentic-LTPO exhibits strong adaptability to dynamic operator policies and effectively enhances the system's long-term performance by 57.2% compared to traditional methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use. Builds on 24 of its 41 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

24 of 41 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Agentic AI for Intent-driven Optimization in Cell-free O-RAN26 Feb
  2. 2026Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management15 Feb
  3. 2025AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks25 Aug

Other references · 21

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  4. 2017Learning to Optimize: Training Deep Neural Networks for Wireless Resource Managementcited by 96
  5. 2020Unfolding WMMSE using Graph Neural Networks for Efficient Power Allocationcited by 61
  6. 2018Model-Driven Deep Learning for Physical Layer Communicationscited by 50
  7. 2018Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networkscited by 34
  8. 2019Deep Learning based Wireless Resource Allocation with Application to Vehicular Networkscited by 19
  9. 2024Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Controlcited by 19
  10. 2024Towards Intent-Based Network Management: Large Language Models for Intent Extraction in 5G Core Networkscited by 15
  11. 2019Making Cell-Free Massive MIMO Competitive With MMSE Processing and Centralized Implementationcited by 13
  12. 2024Designing Network Algorithms via Large Language Modelscited by 11
9 more
  1. 2025Large Language Models for Wireless Communications: From Adaptation to Autonomycited by 11
  2. 2018Ubiquitous Cell-Free Massive MIMO Communicationscited by 8
  3. 2025LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communicationscited by 8
  4. 2023Deep Graph Unfolding for Beamforming in MU-MIMO Interference Networkscited by 6
  5. 2026SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inferencecited by 6
  6. 2019Local Partial Zero-Forcing Precoding for Cell-Free Massive MIMOcited by 4
  7. 2020Joint Trajectory and Passive Beamforming Design for Intelligent Reflecting Surface-Aided UAV Communications: A Deep Reinforcement Learning Approachcited by 4
  8. 2026Multi-Agentic AI for Conflict-Aware rApp Policy Orchestration in Open RANcited by 3
  9. 2025Intent-based Radio Scheduler for RAN Slicing: Learning to deal with different network scenarioscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
  2. 2025Reflection-Driven Self-Optimization 6G Agentic AI RAN via Simulation-in-the-Loop Workflows
  3. 2026ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
  4. 2025Agentic AI for Mobile Network RAN Management and Optimization
  5. 2026Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's Role
  6. 2025Advanced Architectures Integrated with Agentic AI for Next-Generation Wireless Networks
  7. 2026WARA: Toward Automated Wireless Optimization Research with Closed-Loop LLM Agents
  8. 2026Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models